Predicting the Price of an Airbnb Using Math and Python¶

%matplotlib inline
import warnings
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import plotly.express as px
import eli5
from pandas_profiling import ProfileReport
from category_encoders.ordinal import OrdinalEncoder
from xgboost import XGBRegressor
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.feature_selection import SelectKBest, f_regression, chi2
from sklearn.inspection import permutation_importance
from sklearn.pipeline import make_pipeline
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler
from sklearn.impute import SimpleImputer
from sklearn.metrics import r2_score, mean_squared_error, roc_auc_score

# Ignore ugly warning messages
warnings.filterwarnings('ignore')

data_url = './data/ab_us_2020.csv'
df = pd.read_csv(data_url)

print(f"Dataset: {df.shape}")
df.head()

ProfileReport(df)

df.describe()

# Data wrangling function
def wrangle(df):
  df = df.copy()

  # Drop irrelevant features
  df = df.drop(
    columns=['id', 'name', 'host_name', 'neighbourhood_group']
  )

  # Convert last_review to datetime,
  # and replace it with only the month
  df['last_review'] = pd.to_datetime(
    df['last_review'], infer_datetime_format=True
  )
  df['last_review'] = df['last_review'].dt.month

  # Split data iinto feature and target matrices
  target = 'price'
  X = df.drop(target, axis=1)
  y = df[target]

  # Build a preprocessing pipeline to prep features for modeling
  cat_features = [col for col in X.columns if X[col].dtype == 'object']
  num_features = [col for col in X.columns if col not in cat_features]

  cat_pipe = make_pipeline(
    SimpleImputer(strategy='constant', fill_value='missing'), OrdinalEncoder(handle_unknown='return_nan')
  )

  num_pipe = make_pipeline(
    SimpleImputer(strategy='median'), StandardScaler()
  )

  preprocessor = ColumnTransformer(transformers=[
    ('category transformer', cat_pipe, cat_features),
    ('numeric transformer', num_pipe, num_features)
  ])

# Transform the features
  X = preprocessor.fit_transform(X)

# Split the data into training and testing sets
  X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2
  )

  # Return the transformed feature matrices and target vectors
  return X_train, X_test, y_train, y_test

# Drop outlier (minimum_nights = 100000000000000)
df.drop(df['minimum_nights'].argmax(), inplace=True)
print(f"Dataset: {df.shape}")

# Wrangle the data
X_train, X_test, y_train, y_test = wrangle(df)

print(f"""
Training set: {len(X_train) / len(df) *100}%
Testing set: {len(X_test) / len(df) *100}%
""")